Can machine learning approaches predict corporate bankruptcy? Evidence from a qualitative experimental design

Abstract

Bankruptcy prediction has received a growing interest in corporate finance and risk management recently. Although numerous studies in the literature have dealt with various statistical and artificial intelligence classifiers, their performance in credit risk forecasting needs to be further scrutinized compared to other methods. In the spirit of Chen, Härdle and Moro (2011, Quantitative Finance), we design an empirical study to assess the effectiveness of various machine learning topologies trained with big data approaches and qualitative, rather than quantitative, information as input variables. The experimental results from a ten-fold cross-validation methodology demonstrate that a generalized regression neural topology yields an accuracy measurement of 99.96%, a sensitivity measure of 99.91% and specificity of 100%. Indeed, this specific model outperformed multi-layer back-propagation networks, probabilistic neural networks, radial basis functions and regression trees, as well as other advanced classifiers. The utilization of advanced nonlinear classifiers based on big data methodologies and machine learning training generates outperforming results compared to traditional methods for bankruptcy forecasting and risk measurement.

Keywords:

• Credit risk
• Bankruptcy
• Neural networks
• Classifiers
• Experimental design

JEL Classification:

• C32
• C58
• G10
• G17

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

† The specific freely available dataset can be found under the corresponding folder of the repository of the UCL ‘Center for Machine Learning and Intelligent Systems’: https://archive.ics.uci.edu/ml/datasets/Qualitative_Bankruptcy